© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41201
    Prev
    Next
    INDEX
    Explanations

    sentinel behavior or lymph nodes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron identifies the word "sentinel" and related terms, especially in contexts related to surveillance, monitoring, or guarding.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized to detect the token “sentinel” (e.g. in phrases like “sentinel lymph node,” “Sentinel‐1,” or sentinel behavior).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -2.48
     humiliating
    -2.33
    ارتمان
    -2.31
     täglichen
    -2.28
    oucí
    -2.19
    ędzynarod
    -2.17
     enviable
    -2.17
     ihre
    -2.17
    se
    -2.16
     vorigen
    -2.16
    POSITIVE LOGITS
    琑
    2.56
     vpon
    2.42
    ちゃんは
    2.38
    ቍ
    2.19
     and
    2.19
     να
    2.11
    to
    2.11
     europa
    2.08
     extraordinaire
    2.06
    
    2.06
    Activations Density 0.002%

    No Known Activations